Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1101 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1728. Min Act: -0.0000

Data Index: 32773 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1332. Min Act: -0.0000

Data Index: 708566 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1341. Min Act: -0.0000

Data Index: 569035 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1290. Min Act: -0.0000

Data Index: 232676 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1188. Min Act: -0.0000

Data Index: 114037 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1159. Min Act: -0.0000

Data Index: 956872 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1199. Min Act: -0.0000

Data Index: 927572 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1354325 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1126. Min Act: -0.0000

Data Index: 522239 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1065. Min Act: -0.0000

Data Index: 743161 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0938. Min Act: -0.0000

Data Index: 334406 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0984. Min Act: -0.0000

Data Index: 307194 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1052321 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1252638 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1211798 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0920. Min Act: -0.0000

Data Index: 829844 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1465582 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0910. Min Act: -0.0000

Data Index: 992459 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1657081 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 0.1728. Min Range: -0.1728

Max Act: 0.0846. Min Act: -0.0000

Data Index: 517951 (C4 (Web Text))

Max Activating Token Index: 660